Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2240 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.7342. Min Act: -0.0000

Data Index: 678329 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.2710. Min Act: -0.0000

Data Index: 499867 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.2457. Min Act: -0.0000

Data Index: 471275 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.1150. Min Act: -0.0000

Data Index: 495594 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.2144. Min Act: -0.0000

Data Index: 739649 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.2062. Min Act: -0.0000

Data Index: 944053 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.1846. Min Act: -0.0000

Data Index: 1353870 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.2891. Min Act: -0.0000

Data Index: 961383 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.1430. Min Act: -0.0000

Data Index: 425418 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.1462. Min Act: -0.0000

Data Index: 415634 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.1306. Min Act: -0.0000

Data Index: 1268988 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.1192. Min Act: -0.0000

Data Index: 716531 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 2.7342. Min Range: -2.7342

Max Act: 1.9984. Min Act: -0.0000

Data Index: 1211445 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.3136. Min Act: -0.0000

Data Index: 865327 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.0970. Min Act: -0.0000

Data Index: 1307738 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.0466. Min Act: -0.0000

Data Index: 1353906 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.0446. Min Act: -0.0000

Data Index: 958996 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 2.7342. Min Range: -2.7342

Max Act: 1.9430. Min Act: -0.0000

Data Index: 175982 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 2.7342. Min Range: -2.7342

Max Act: 1.9331. Min Act: -0.0000

Data Index: 1206940 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 2.7342. Min Range: -2.7342

Max Act: 2.1348. Min Act: -0.0000

Data Index: 946341 (C4 (Web Text))

Max Activating Token Index: 33